Using polygenic scores and clinical data for bipolar disorder patient stratification and lithium response prediction: machine learning approach

被引:20
作者
Cearns, Micah [1 ]
Amare, Azmeraw T. [1 ]
Schubert, Klaus Oliver [1 ,2 ]
Thalamuthu, Anbupalam [3 ]
Frank, Joseph [4 ]
Streit, Fabian [4 ]
Adli, Mazda [5 ]
Akula, Nirmala [6 ]
Akiyama, Kazufumi [7 ]
Ardau, Raffaella [8 ]
Arias, Barbara [9 ,10 ]
Aubry, Jean-Michel [11 ]
Backlund, Lena [6 ,12 ,13 ]
Bhattacharjee, Abesh Kumar [14 ]
Bellivier, Frank [15 ]
Benabarre, Antonio [16 ]
Bengesser, Susanne [17 ]
Biernacka, Joanna M. [18 ,19 ]
Birner, Armin [17 ]
Brichant-Petitjean, Clara [15 ]
Cervantes, Pablo [20 ]
Chen, Hsi-Chung [21 ,22 ]
Chillotti, Caterina [8 ]
Cichon, Sven [23 ,24 ,25 ]
Cruceanu, Cristiana [26 ]
Czerski, Piotr M. [27 ]
Dalkner, Nina [17 ]
Dayer, Alexandre [11 ]
Degenhardt, Franziska [23 ,24 ]
Del Zompo, Maria [28 ]
De Paulo, J. Raymond [6 ,29 ]
Etain, Bruno [15 ]
Falkai, Peter [30 ]
Forstner, Andreas J. [23 ,24 ,25 ,31 ]
Frisen, Louise [12 ,13 ]
Frye, Mark A. [19 ]
Fullerton, Janice M. [32 ]
Gard, Sebastien [33 ]
Garnham, Julie S. [34 ]
Goes, Fernando S. [29 ]
Grigoroiu-Serbanescu, Maria [35 ]
Grof, Paul [36 ]
Hashimoto, Ryota [37 ,38 ]
Hauser, Joanna [27 ]
Heilbronner, Urs [39 ,40 ]
Herms, Stefan [23 ,24 ,25 ]
Hoffmann, Per [23 ,24 ,25 ]
Hofmann, Andrea [23 ,24 ]
Hou, Liping [6 ]
Hsu, Yi Hsiang [41 ,42 ]
机构
[1] Univ Adelaide, Sch Med, Discipline Psychiat, Adelaide, SA, Australia
[2] Northern Adelaide Local Hlth Network, Mental Hlth Serv, Adelaide, SA, Australia
[3] Univ New South Wales, Ctr Hlth Brain Ageing CHeBA, Sch Psychiat, Sydney, NSW, Australia
[4] Heidelberg Univ, Med Fac Mannheim, Cent Inst Mental Hlth, Dept Genet Epidemiol Psychiat, Heidelberg, Germany
[5] Charite Univ Med Berlin, Dept Psychiat & Psychotherapy, Campus Charite Mitte, Berlin, Germany
[6] NIMH, Intramural Res Program, NIH, US Dept HHS, Bethesda, MD 20892 USA
[7] Dokkyo Med Univ, Dept Biol Psychiat & Neurosci, Sch Med, Mibu, Tochigi, Japan
[8] Hosp Univ Agcy Cagliari, Unit Clin Pharmacol, Cagliari, Italy
[9] Univ Barcelona, Fac Biol, Unitat Zool & Antropol Biol, CIBERSAM,Dept Biol Evolut Ecol & Ciencias Ambient, Barcelona, Spain
[10] Univ Barcelona, CIBERSAM, Inst Biomed IBUB, Barcelona, Spain
[11] HUG Geneva Univ Hosp, Dept Psychiat, Mood Disorders Unit, Geneva, Switzerland
[12] Karolinska Inst, Dept Mol Med & Surg, Stockholm, Sweden
[13] Karolinska Univ Hosp, Ctr Mol Med, Stockholm, Sweden
[14] Univ Calif San Diego, Dept Psychiat, La Jolla, CA USA
[15] Univ Paris Diderot, INSERM UMR S 1144, Dept Psychiat & Med Addictol, Grp Hosp St Louis Lariboisiere F Widal,AP HP, Paris, France
[16] Univ Barcelona, Hosp Clin, Inst Neurosci, CIBERSAM,Bipolar Disorder Program, Barcelona, Spain
[17] Med Univ Graz, Dept Psychiat & Psychotherapeut Med, Res Unit Bipolar Affect Disorder, Graz, Austria
[18] Mayo Clin, Dept Hlth Sci Res, Rochester, MN USA
[19] Mayo Clin, Dept Psychiat & Psychol, Rochester, MN USA
[20] McGill Univ Hlth Ctr, Neuromodulat Unit, Montreal, PQ, Canada
[21] Natl Taiwan Univ Hosp, Dept Psychiat, Taipei, Taiwan
[22] Natl Taiwan Univ Hosp, Ctr Sleep Disorders, Taipei, Taiwan
[23] Univ Bonn, Inst Human Genet, Bonn, Germany
[24] Life & Brain Ctr, Dept Genom, Bonn, Germany
[25] Univ Hosp Basel, Dept Biomed, Human Genom Res Grp, Basel, Switzerland
[26] McGill Univ, Douglas Mental Hlth Univ Inst, Montreal, PQ, Canada
[27] Poznan Univ Med Sci, Psychiat Genet Unit, Poznan, Poland
[28] Univ Cagliari, Dept Biomed Sci, Cagliari, Italy
[29] Johns Hopkins Univ, Dept Psychiat & Behav Sci, Baltimore, MD 21218 USA
[30] Ludwig Maximilian Univ Munich, Dept Psychiat & Psychotherapy, Munich, Germany
[31] Univ Basel, Dept Psychiat UPK, Basel, Switzerland
[32] Univ New South Wales, Australia Janice M Fullerton Sch Med Sci, Neurosci Res Australia, Sydney, NSW, Australia
[33] Hop Charles Perrens, Serv Psychiat, Bordeaux, France
[34] Dalhousie Univ, Dept Psychiat, Halifax, NS, Canada
[35] Alexandru Obregia Clin Psychiat Hosp, Biometr Psychiat Genet Res Unit, Bucharest, Romania
[36] Mood Disorders Ctr Ottawa, Ottawa, ON, Canada
[37] Osaka Univ, Mol Res Ctr Childrens Mental Dev, United Grad Sch Child Dev, Osaka, Japan
[38] Osaka Univ, Dept Psychiat, Grad Sch Med, Osaka, Japan
[39] Ludwig Maximilians Univ Munchen, Inst Psychiat Phen & Genom IPPG, Univ Hosp, Munich, Germany
[40] Georg August Univ Gottingen, Univ Med Ctr UMG, Dept Psychiat & Psychotherapy, Gottingen, Germany
[41] Harvard Sch Publ Hlth, Program Quantitat Genom, Boston, MA USA
[42] Harvard Med Sch, HSL Inst Aging Res, Boston, MA 02115 USA
[43] Univ Paris Est Creteil, INSERM, Translat Neuropsychiat, Fdn FondaMental,IMRB, Creteil, France
[44] Univ Lorraine, Serv Psychiat & Psychol Clin, Ctr Psychotherap Nancy, Nancy, France
[45] Natl Taiwan Univ, Coll Publ Hlth, Dept Publ Hlth, Taipei, Taiwan
[46] Natl Taiwan Univ, Coll Publ Hlth, Inst Epidemiol & Prevent Med, Taipei, Taiwan
[47] Juntendo Univ, Grad Sch Med, Dept Psychiat & Behav Sci, Tokyo, Japan
[48] Univ Hosp Frankfurt, Dept Psychiat Psychosomat Med & Psychotherapy, Frankfurt, Germany
[49] Poznan Univ Med Sci, Dept Adult Psychiat, Poznan, Poland
[50] Landesklinikum Neunkirchen, Dept Psychiat & Psychotherapeut Med, Neunkirchen, Austria
基金
英国医学研究理事会; 瑞士国家科学基金会; 瑞典研究理事会; 加拿大健康研究院; 美国国家卫生研究院;
关键词
Mood stabilisers; bipolar affective disorders; genetics; outcome studies; depressive disorders; PSYCHIATRIC-DISORDERS; COMPARATIVE EFFICACY; SCHIZOPHRENIA; NETWORK; MANIA;
D O I
10.1192/bjp.2022.28
中图分类号
R749 [精神病学];
学科分类号
100205 ;
摘要
Background Response to lithium in patients with bipolar disorder is associated with clinical and transdiagnostic genetic factors. The predictive combination of these variables might help clinicians better predict which patients will respond to lithium treatment. Aims To use a combination of transdiagnostic genetic and clinical factors to predict lithium response in patients with bipolar disorder. Method This study utilised genetic and clinical data (n = 1034) collected as part of the International Consortium on Lithium Genetics (ConLi(+)Gen) project. Polygenic risk scores (PRS) were computed for schizophrenia and major depressive disorder, and then combined with clinical variables using a cross-validated machine-learning regression approach. Unimodal, multimodal and genetically stratified models were trained and validated using ridge, elastic net and random forest regression on 692 patients with bipolar disorder from ten study sites using leave-site-out cross-validation. All models were then tested on an independent test set of 342 patients. The best performing models were then tested in a classification framework. Results The best performing linear model explained 5.1% (P = 0.0001) of variance in lithium response and was composed of clinical variables, PRS variables and interaction terms between them. The best performing non-linear model used only clinical variables and explained 8.1% (P = 0.0001) of variance in lithium response. A priori genomic stratification improved non-linear model performance to 13.7% (P = 0.0001) and improved the binary classification of lithium response. This model stratified patients based on their meta-polygenic loadings for major depressive disorder and schizophrenia and was then trained using clinical data. Conclusions Using PRS to first stratify patients genetically and then train machine-learning models with clinical predictors led to large improvements in lithium response prediction. When used with other PRS and biological markers in the future this approach may help inform which patients are most likely to respond to lithium treatment.
引用
收藏
页码:219 / 228
页数:10
相关论文
共 42 条
[1]   The genetic overlap between mood disorders and cardiometabolic diseases: a systematic review of genome wide and candidate gene studies [J].
Amare, A. T. ;
Schubert, K. O. ;
Klingler-Hoffmann, M. ;
Cohen-Woods, S. ;
Baune, B. T. .
TRANSLATIONAL PSYCHIATRY, 2017, 7 :e1007-e1007
[2]   Association of polygenic score for major depression with response to lithium in patients with bipolar disorder [J].
Amare, Azmeraw T. ;
Schubert, Klaus Oliver ;
Hou, Liping ;
Clark, Scott R. ;
Papiol, Sergi ;
Cearns, Micah ;
Heilbronner, Urs ;
Degenhardt, Franziska ;
Tekola-Ayele, Fasil ;
Hsu, Yi-Hsiang ;
Shekhtman, Tatyana ;
AdIi, Mazda ;
Akula, Nirmala ;
Akiyama, Kazufumi ;
Ardau, Raffaella ;
Arias, Barbara ;
Aubry, Jean-Michel ;
Backlund, Lena ;
Bhattacharjee, Kumar ;
Bellivier, Frank ;
Benabarre, Antonio ;
Bengesser, Susanne ;
Biernacka, Joanna M. ;
Birner, Armin ;
Brichant-Petitjean, Clara ;
Cervantes, Pablo ;
Chen, Hsi-Chung ;
Chillotti, Caterina ;
Cichon, Sven ;
Cruceanu, Cristiana ;
Czerski, Piotr M. ;
Dalkner, Nina ;
Dayer, Alexandre ;
Del Zompo, Maria ;
DePaulo, J. Raymond ;
Etain, Bruno ;
Jamain, Stephane ;
Falkai, Peter ;
Forstner, Andreas J. ;
Frisen, Louise ;
Frye, Mark A. ;
Fullerton, Janice M. ;
Gard, Sebastien ;
Garnham, Julie S. ;
Goes, Fernando S. ;
Grigoroiu-Serbanescu, Maria ;
Grof, Paul ;
Hashimoto, Ryota ;
Hauser, Joanna ;
Herms, Stefan .
MOLECULAR PSYCHIATRY, 2021, 26 (06) :2457-2470
[3]   Association of Polygenic Score for Schizophrenia and HLA Antigen and Inflammation Genes With Response to Lithium in Bipolar Affective Disorder A Genome-Wide Association Study [J].
Amare, Azmeraw T. ;
Schubert, Klaus Oliver ;
Hou, Liping ;
Clark, Scott R. ;
Papiol, Sergi ;
Heilbronner, Urs ;
Degenhardt, Franziska ;
Tekola-Ayele, Fasil ;
Hsu, Yi-Hsiang ;
Shekhtman, Tatyana ;
Adli, Mazda ;
Akula, Nirmala ;
Akiyama, Kazufumi ;
Ardau, Raffaella ;
Arias, Barbara ;
Aubry, Jean-Michel ;
Backlund, Lena ;
Bhattacharjee, Abesh Kumar ;
Bellivier, Frank ;
Benabarre, Antonio ;
Bengesser, Susanne ;
Biernacka, Joanna M. ;
Birner, Armin ;
Brichant-Petitjean, Clara ;
Cervantes, Pablo ;
Chen, Hsi-Chung ;
Chillotti, Caterina ;
Cichon, Sven ;
Cruceanu, Cristiana ;
Czerski, Piotr M. ;
Dalkner, Nina ;
Dayer, Alexandre ;
Del Zompo, Maria ;
DePaulo, J. Raymond ;
Etain, Bruno ;
Falkai, Peter ;
Forstner, Andreas J. ;
Frisen, Louise ;
Frye, Mark A. ;
Fullerton, Janice M. ;
Gard, Sebastien ;
Garnham, Julie S. ;
Goes, Fernando S. ;
Grigoroiu-Serbanescu, Maria ;
Grof, Paul ;
Hashimoto, Ryota ;
Hauser, Joanna ;
Herms, Stefan ;
Hoffmann, Per ;
Hofmann, Andrea .
JAMA PSYCHIATRY, 2018, 75 (01) :65-74
[4]   A Pattern of Cognitive Deficits Stratified for Genetic and Environmental Risk Reliably Classifies Patients With Schizophrenia From Healthy Control Subjects [J].
Antonucci, Linda A. ;
Pergola, Giulio ;
Pigoni, Alessandro ;
Dwyer, Dominic ;
Kambeitz-Ilankovic, Lana ;
Penzel, Nora ;
Romano, Raffaella ;
Gelao, Barbara ;
Torretta, Silvia ;
Rampino, Antonio ;
Trojano, Maria ;
Caforio, Grazia ;
Falkai, Peter ;
Blasi, Giuseppe ;
Koutsouleris, Nikolaos ;
Bertolino, Alessandro .
BIOLOGICAL PSYCHIATRY, 2020, 87 (08) :697-707
[5]   Multiple imputation by chained equations: what is it and how does it work? [J].
Azur, Melissa J. ;
Stuart, Elizabeth A. ;
Frangakis, Constantine ;
Leaf, Philip J. .
INTERNATIONAL JOURNAL OF METHODS IN PSYCHIATRIC RESEARCH, 2011, 20 (01) :40-49
[6]  
Biau G, 2008, J MACH LEARN RES, V9, P2015
[7]  
Buhmann JM, 1999, INTERNATIONAL CONFERENCE ON ADVANCES IN PATTERN RECOGNITION, P167
[8]   Machine learning probability calibration for high-risk clinical decision-making [J].
Cearns, Micah ;
Hahn, Tim ;
Clark, Scott ;
Baune, Bernhard T. .
AUSTRALIAN AND NEW ZEALAND JOURNAL OF PSYCHIATRY, 2020, 54 (02) :123-126
[9]   Recommendations and future directions for supervised machine learning in psychiatry [J].
Cearns, Micah ;
Hahn, Tim ;
Baune, Bernhard T. .
TRANSLATIONAL PSYCHIATRY, 2019, 9 (1)
[10]   Comparative efficacy and acceptability of antimanic drugs in acute mania: a multiple-treatments meta-analysis [J].
Cipriani, Andrea ;
Barbui, Corrado ;
Salanti, Georgia ;
Rendell, Jennifer ;
Brown, Rachel ;
Stockton, Sarah ;
Purgato, Marianna ;
Spineli, Loukia M. ;
Goodwin, Guy M. ;
Geddes, John R. .
LANCET, 2011, 378 (9799) :1306-1315